论文标题
零资源跨域命名实体识别
Zero-Resource Cross-Domain Named Entity Recognition
论文作者
论文摘要
跨域命名实体识别（NER）的现有模型依赖于目标域中的许多未标记的语料库或标记为NER培训数据。但是，收集低资源目标域的数据不仅昂贵，而且耗时。因此，我们提出了一个不使用任何外部资源的跨域NER模型。我们首先通过添加一个新的目标函数来检测令牌是否命名实体来引入多任务学习（MTL）。然后，我们引入了一个称为实体专家（MOEE）混合物的框架，以改善零资源域适应性的鲁棒性。最后，实验结果表明，我们的模型优于强大的无监督跨域序列标签模型，并且我们的模型的性能接近了利用大量资源的最新模型的性能。
Existing models for cross-domain named entity recognition (NER) rely on numerous unlabeled corpus or labeled NER training data in target domains. However, collecting data for low-resource target domains is not only expensive but also time-consuming. Hence, we propose a cross-domain NER model that does not use any external resources. We first introduce a Multi-Task Learning (MTL) by adding a new objective function to detect whether tokens are named entities or not. We then introduce a framework called Mixture of Entity Experts (MoEE) to improve the robustness for zero-resource domain adaptation. Finally, experimental results show that our model outperforms strong unsupervised cross-domain sequence labeling models, and the performance of our model is close to that of the state-of-the-art model which leverages extensive resources.
